DialogLab: Authoring, Simulating, and Testing Dynamic Human-AI Group Conversations
Abstract
Designing compelling multi-party conversations involving both humans and AI agents presents significant challenges, particularly in balancing scripted structure with emergent, human-like interactions. We introduce DialogLab, a prototyping toolkit for authoring, simulating, and testing hybrid human-AI dialogues. DialogLab provides a unified interface to configure conversational scenes, define agent personas, manage group structures, specify turn-taking rules, and orchestrate transitions between scripted narratives and improvisation. Crucially, DialogLab allows designers to introduce controlled deviations from the script—through configurable agents that emulate human unpredictability—to systematically probe how conversations adapt and recover. DialogLab facilitates rapid iteration and evaluation of complex, dynamic multi-party human-AI dialogues. An evaluation with both end users and domain experts demonstrates that DialogLab supports efficient iteration and structured verification, with applications in training, rehearsal, and research on social dynamics. Our findings show the value of integrating real-time, human-in-the-loop improvisation with structured scripting to support more realistic and adaptable multi-party conversation design.
BibTeX
@inproceedings{10.1145/3746059.3747696,
author = {Hu, Erzhen and Chen, Yanhe and Li, Mingyi and Phadnis, Vrushank and Xu, Pingmei and Qian, Xun and Olwal, Alex and Kim, David and Heo, Seongkook and Du, Ruofei},
title = {DialogLab: Authoring, Simulating, and Testing Dynamic Human-AI Group Conversations},
year = {2025},
isbn = {9798400720376},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3746059.3747696},
doi = {10.1145/3746059.3747696},
abstract = {Designing compelling multi-party conversations involving both humans and AI agents presents significant challenges, particularly in balancing scripted structure with emergent, human-like interactions. We introduce DialogLab, a prototyping toolkit for authoring, simulating, and testing hybrid human-AI dialogues. DialogLab provides a unified interface to configure conversational scenes, define agent personas, manage group structures, specify turn-taking rules, and orchestrate transitions between scripted narratives and improvisation. Crucially, DialogLab allows designers to introduce controlled deviations from the script—through configurable agents that emulate human unpredictability—to systematically probe how conversations adapt and recover. DialogLab facilitates rapid iteration and evaluation of complex, dynamic multi-party human-AI dialogues. An evaluation with both end users and domain experts demonstrates that DialogLab supports efficient iteration and structured verification, with applications in training, rehearsal, and research on social dynamics. Our findings show the value of integrating real-time, human-in-the-loop improvisation with structured scripting to support more realistic and adaptable multi-party conversation design.},
booktitle = {Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology},
articleno = {210},
numpages = {20},
keywords = {human-AI interaction, dialogues, multi-party conversation, real-time communication, conversation simulation, human-agent interaction, large language model},
location = {
},
series = {UIST '25}
}